Camouflage learning. Feature value obscuring ambient intelligence for constrained devices. Nguyen, L. N., Sigg, S., Lietzen, J., Findling, R. D., & Ruttik, K. IEEE Transactions on Mobile Computing, IEEE, 2021. abstract bibtex Ambient intelligence demands collaboration schemes for distributed constrained devices which are not only highly energy efficient in distributed sensing, processing and communication, but which also respect data privacy. Traditional algorithms for distributed processing suffer in Ambient intelligence domains either from limited data privacy, or from their excessive processing demands for constrained distributed devices. In this paper, we present Camouflage learning, a distributed machine learning scheme that obscures the trained model via probabilistic collaboration using physical-layer computation offloading and demonstrate the feasibility of the approach on backscatter communication prototypes and in comparison with Federated learning. We show that Camouflage learning is more energy efficient than traditional schemes and that it requires less communication overhead while reducing the computation load through physical-layer computation offloading. The scheme is synchronization-agnostic and thus appropriate for sharply constrained, synchronization-incapable devices. We demonstrate model training and inference on four distinct datasets and investigate the performance of the scheme with respect to communication range, impact of challenging communication environments, power consumption, and the backscatter hardware prototype.
@article{Le_2021_TMC,
author={Le Ngu Nguyen and Stephan Sigg and Jari Lietzen and Rainhard Dieter Findling and Kalle Ruttik},
journal={IEEE Transactions on Mobile Computing},
title={Camouflage learning. Feature value obscuring ambient intelligence for constrained devices},
year={2021},
abstract={Ambient intelligence demands collaboration schemes for distributed constrained devices which are not only highly energy efficient in distributed sensing, processing and communication, but which also respect data privacy. Traditional algorithms for distributed processing suffer in Ambient intelligence domains either from limited data privacy, or from their excessive processing demands for constrained distributed devices.
In this paper, we present Camouflage learning, a distributed machine learning scheme that obscures the trained model via probabilistic collaboration using physical-layer computation offloading and demonstrate the feasibility of the approach on backscatter communication prototypes and in comparison with Federated learning. We show that Camouflage learning is more energy efficient than traditional schemes and that it requires less communication overhead while reducing the computation load through physical-layer computation offloading. The scheme is synchronization-agnostic and thus appropriate for sharply constrained, synchronization-incapable devices. We demonstrate model training and inference on four distinct datasets and investigate the performance of the scheme with respect to communication range, impact of challenging communication environments, power consumption, and the backscatter hardware prototype.
},
issue_date = {July 2021},
publisher = {IEEE},
volume = { },
number = { },
pages = {1-17},
group = {ambience},
project = {abacus}
}
Downloads: 0
{"_id":"2hJ9GvukWTH8EY6cE","bibbaseid":"nguyen-sigg-lietzen-findling-ruttik-camouflagelearningfeaturevalueobscuringambientintelligenceforconstraineddevices-2021","author_short":["Nguyen, L. N.","Sigg, S.","Lietzen, J.","Findling, R. D.","Ruttik, K."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Le","Ngu"],"propositions":[],"lastnames":["Nguyen"],"suffixes":[]},{"firstnames":["Stephan"],"propositions":[],"lastnames":["Sigg"],"suffixes":[]},{"firstnames":["Jari"],"propositions":[],"lastnames":["Lietzen"],"suffixes":[]},{"firstnames":["Rainhard","Dieter"],"propositions":[],"lastnames":["Findling"],"suffixes":[]},{"firstnames":["Kalle"],"propositions":[],"lastnames":["Ruttik"],"suffixes":[]}],"journal":"IEEE Transactions on Mobile Computing","title":"Camouflage learning. Feature value obscuring ambient intelligence for constrained devices","year":"2021","abstract":"Ambient intelligence demands collaboration schemes for distributed constrained devices which are not only highly energy efficient in distributed sensing, processing and communication, but which also respect data privacy. Traditional algorithms for distributed processing suffer in Ambient intelligence domains either from limited data privacy, or from their excessive processing demands for constrained distributed devices. In this paper, we present Camouflage learning, a distributed machine learning scheme that obscures the trained model via probabilistic collaboration using physical-layer computation offloading and demonstrate the feasibility of the approach on backscatter communication prototypes and in comparison with Federated learning. We show that Camouflage learning is more energy efficient than traditional schemes and that it requires less communication overhead while reducing the computation load through physical-layer computation offloading. The scheme is synchronization-agnostic and thus appropriate for sharply constrained, synchronization-incapable devices. We demonstrate model training and inference on four distinct datasets and investigate the performance of the scheme with respect to communication range, impact of challenging communication environments, power consumption, and the backscatter hardware prototype. ","issue_date":"July 2021","publisher":"IEEE","volume":"","number":"","pages":"1-17","group":"ambience","project":"abacus","bibtex":"@article{Le_2021_TMC,\nauthor={Le Ngu Nguyen and Stephan Sigg and Jari Lietzen and Rainhard Dieter Findling and Kalle Ruttik},\njournal={IEEE Transactions on Mobile Computing},\ntitle={Camouflage learning. Feature value obscuring ambient intelligence for constrained devices},\nyear={2021},\nabstract={Ambient intelligence demands collaboration schemes for distributed constrained devices which are not only highly energy efficient in distributed sensing, processing and communication, but which also respect data privacy. Traditional algorithms for distributed processing suffer in Ambient intelligence domains either from limited data privacy, or from their excessive processing demands for constrained distributed devices. \nIn this paper, we present Camouflage learning, a distributed machine learning scheme that obscures the trained model via probabilistic collaboration using physical-layer computation offloading and demonstrate the feasibility of the approach on backscatter communication prototypes and in comparison with Federated learning. We show that Camouflage learning is more energy efficient than traditional schemes and that it requires less communication overhead while reducing the computation load through physical-layer computation offloading. The scheme is synchronization-agnostic and thus appropriate for sharply constrained, synchronization-incapable devices. We demonstrate model training and inference on four distinct datasets and investigate the performance of the scheme with respect to communication range, impact of challenging communication environments, power consumption, and the backscatter hardware prototype.\n},\nissue_date = {July 2021},\npublisher = {IEEE},\nvolume = { },\nnumber = { },\npages = {1-17},\ngroup = {ambience},\nproject = {abacus}\n}\n\n\n","author_short":["Nguyen, L. N.","Sigg, S.","Lietzen, J.","Findling, R. D.","Ruttik, K."],"key":"Le_2021_TMC","id":"Le_2021_TMC","bibbaseid":"nguyen-sigg-lietzen-findling-ruttik-camouflagelearningfeaturevalueobscuringambientintelligenceforconstraineddevices-2021","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://ambientintelligence.aalto.fi/bibtex/LiteraturAll","dataSources":["aPfcTvMp5jE2KuS7H","a6QYyvmdLfrsx7DiL"],"keywords":[],"search_terms":["camouflage","learning","feature","value","obscuring","ambient","intelligence","constrained","devices","nguyen","sigg","lietzen","findling","ruttik"],"title":"Camouflage learning. Feature value obscuring ambient intelligence for constrained devices","year":2021}